Aspiring AI safety researcher with an unconventional path into the field.
My background is in corporate finance and analytics. I’ve worked in production finance on shows including MasterChef, Big Brother, and The Biggest Loser, as well as in cybersecurity at a Fortune 500 company. I earned a B.A. in Economics from UC Santa Cruz in 2013 and, more recently, an M.S. in Business Analytics from Pepperdine Graziadio Business School in 2025.
I started to become seriously interested in AI safety around late 2024 after, admittedly, watching way too many AI doom-and-gloom videos. That curiosity quickly turned into a deeper scientific interest in the research itself which led me to the current AI safety literature and studying mechanistic interpretability.
My current interests focus on AI safety and mechanistic interpretability. I’m hoping to pursue a PhD in Tokyo and eventually participate in research programs such as MATS, with the longer-term goal of working full-time on AI safety research.